The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to run static analysis tools, including npx eslint, bandit, and grep, against the current codebase.
[EXTERNAL_DOWNLOADS]: The instructions include downloading security auditing tools from established sources, such as pip install bandit and go install from the official golang.org repository.
[PROMPT_INJECTION]: The skill processes untrusted external data (the codebase being scanned) to identify vulnerabilities. This represents an indirect prompt injection surface where malicious code could attempt to influence the agent's findings, although the use of specialized scanners and structured report formatting provides defensive layers.

vulnerability-scanner